Model catalog

GPT-5.3 Codex SparkOpenAI

GPT-5.3 Codex Spark accepts text, images, PDFs and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 32,000 tokens.

Kling 3.0 Pro Image to VideoKling AI

Kling 3.0 Pro Image to Video accepts text, images and returns video.

Kling 3.0 Pro Text to VideoKling AI

Kling 3.0 Pro Text to Video accepts text and returns video.

Kling 3.0 Standard Image to VideoKling AI

Kling 3.0 Standard Image to Video accepts text, images and returns video.

Kling 3.0 Standard Text to VideoKling AI

Kling 3.0 Standard Text to Video accepts text and returns video.

Qwen3 Coder NextAlibaba

Qwen3 Coder Next accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Step 3.5 FlashStepFun (China)

Step 3.5 Flash accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.

DeepSeek OCR 2DeepSeek

DeepSeek OCR 2 accepts text, images and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 8,192 tokens.

MiniMax-M2 HerMiniMax (minimax.io)

MiniMax-M2 Her accepts text and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 2,048 tokens.

GLM-4.7-FlashZhipu AI

GLM-4.7-Flash accepts text and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 131,072 tokens.

GLM-4.7-FlashXZhipu AI

GLM-4.7-FlashX accepts text and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 131,072 tokens.

Jamba MiniAI21 Labs

Jamba Mini accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 4,096 tokens.

Kimi K2.5Moonshot AI

Kimi K2.5 accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Solar Pro 3Upstage

Solar Pro 3 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

Seed 1.8Bytedance Seed

Seed 1.8 accepts text, images and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 64,000 tokens.

MiniMax-M2.1MiniMax (minimax.io)

MiniMax-M2.1 accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

GLM-4.7Zhipu AI

GLM-4.7 accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

X-Ai/Grok-4-Fast-Non-ReasoningxAI

X-Ai/Grok-4-Fast-Non-Reasoning accepts text, images, audio, video and returns text. The canonical context window is 2,000,000 tokens. The canonical maximum output is 2,000,000 tokens.

Gemini 3 Flash PreviewGoogle

Gemini 3 Flash Preview accepts text, images, video, audio, PDFs and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

MiMo-V2-FlashXiaomi

MiMo-V2-Flash accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Nemotron 3 Nano 30B A3BNvidia

Nemotron 3 Nano 30B A3B accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

GPT-5.2OpenAI

GPT-5.2 accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-5.2 ChatOpenAI

GPT-5.2 Chat accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 16,384 tokens.

GPT-5.2 CodexOpenAI

GPT-5.2 Codex accepts text, images, PDFs and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.